codezakh commited on
Commit
dab7fa3
·
verified ·
1 Parent(s): 8df347e

Upload folder using huggingface_hub

Browse files
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openai/gpt-oss-20b",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": false,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 32,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": "all-linear",
27
+ "task_type": "CAUSAL_LM",
28
+ "trainable_token_indices": null,
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed7cd12d4e16a8e10cc9e289255461dc5a89244a86f7d9781f14f97c96c66be
3
+ size 965742648
training_artifact.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "trainer_kind": "grpo",
3
+ "base_model": "openai/gpt-oss-20b",
4
+ "renderer_name": "gpt_oss_medium_reasoning",
5
+ "checkpoint_uri": "tinker://103b7c28-6715-5755-9482-d2ea06acaa2f:train:0/sampler_weights/final",
6
+ "token_usage": {
7
+ "sampling_input_tokens": 6801392,
8
+ "sampling_output_tokens": 3661879,
9
+ "num_examples": 2322,
10
+ "num_steps": 20
11
+ },
12
+ "trainer_config_snapshot": {
13
+ "kind": "grpo",
14
+ "base_model": "openai/gpt-oss-20b",
15
+ "renderer_name": "gpt_oss_medium_reasoning",
16
+ "learning_rate": 0.00004,
17
+ "group_size": 8,
18
+ "groups_per_batch": 8,
19
+ "num_iters": 20,
20
+ "save_every": 5,
21
+ "max_tokens": 8192,
22
+ "lora_rank": 32,
23
+ "temperature": 1.0,
24
+ "reward": {
25
+ "kind": "correctness_crps"
26
+ }
27
+ }
28
+ }