BART-ender commited on
Commit
568e5bc
·
verified ·
1 Parent(s): cf5dcbd

Upload folder using huggingface_hub

Browse files
blue_cycle_1/adapter_config.json CHANGED
@@ -34,8 +34,8 @@
34
  "rank_pattern": {},
35
  "revision": null,
36
  "target_modules": [
37
- "q_proj",
38
- "v_proj"
39
  ],
40
  "target_parameters": null,
41
  "task_type": "CAUSAL_LM",
 
34
  "rank_pattern": {},
35
  "revision": null,
36
  "target_modules": [
37
+ "v_proj",
38
+ "q_proj"
39
  ],
40
  "target_parameters": null,
41
  "task_type": "CAUSAL_LM",
blue_cycle_1/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d81a8869746a3cce0238b90ae22f1555ede481ec8b1c4a6c5a4168189c996f2a
3
  size 2175168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863a2a8f7dc3f0c4b421e968844eb13512338b48eeda88d57b7fa5777085f69e
3
  size 2175168
blue_cycle_1/best_metrics.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metric": "train/loss",
3
- "best_loss": -0.01885230392217636,
4
- "best_step": 155,
5
  "agent_type": "blue"
6
  }
 
1
  {
2
  "metric": "train/loss",
3
+ "best_loss": 0.03103274405002594,
4
+ "best_step": 15,
5
  "agent_type": "blue"
6
  }
blue_cycle_1/blue_init/adapter_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.19.1",
32
+ "qalora_group_size": 16,
33
+ "r": 8,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "v_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_bdlora": null,
44
+ "use_dora": false,
45
+ "use_qalora": false,
46
+ "use_rslora": false
47
+ }
blue_cycle_1/blue_init/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23fb722cc72c0da19c83924c33c0c1064ab873681338b4d4fe6d76e444d77816
3
+ size 2175168