Hugging Face's logo

grounded-ai
/
phi3.5-rag-relevance-judge

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Jlonge4 commited on
Commit
58bb8d6
•
1 Parent(s): 172ac59

Jlonge4/rag-rel

Browse files
Files changed (12) hide show
  1. README.md +19 -19
  2. adapter_config.json +6 -6
  3. adapter_model.safetensors +1 -1
  4. runs/Oct13_18-18-49_48c91bda07e0/events.out.tfevents.1728843530.48c91bda07e0.9895.0 +3 -0
  5. runs/Oct13_18-20-53_48c91bda07e0/events.out.tfevents.1728843654.48c91bda07e0.9895.1 +3 -0
  6. runs/Oct13_18-21-27_48c91bda07e0/events.out.tfevents.1728843688.48c91bda07e0.11185.0 +3 -0
  7. runs/Oct13_18-23-33_48c91bda07e0/events.out.tfevents.1728843814.48c91bda07e0.11185.1 +3 -0
  8. runs/Oct13_18-24-23_48c91bda07e0/events.out.tfevents.1728843864.48c91bda07e0.12055.0 +3 -0
  9. runs/Oct13_18-25-58_48c91bda07e0/events.out.tfevents.1728843959.48c91bda07e0.12055.1 +3 -0
  10. runs/Oct13_18-26-54_48c91bda07e0/events.out.tfevents.1728844015.48c91bda07e0.12055.2 +3 -0
  11. runs/Oct13_18-28-24_48c91bda07e0/events.out.tfevents.1728844105.48c91bda07e0.13277.0 +3 -0
  12. training_args.bin +1 -1
README.md CHANGED
@@ -16,12 +16,12 @@ model-index:
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/grounded-ai-rag-relevance/runs/bnvts1hx)
20
  # grounded-ai-rag-3
21
 
22
  This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 1.4248
25
  - Rouge1: 1.0
26
  - Rouge2: 0.0
27
  - Rougel: 1.0
@@ -44,12 +44,12 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 5e-05
48
  - train_batch_size: 2
49
  - eval_batch_size: 8
50
  - seed: 42
51
- - gradient_accumulation_steps: 4
52
- - total_train_batch_size: 8
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: cosine
55
  - lr_scheduler_warmup_steps: 15
@@ -59,20 +59,20 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
61
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
62
- | 1.0354 | 5.0 | 5 | 1.7161 | 1.0 | 0.0 | 1.0 | 1.0 |
63
- | 0.9393 | 10.0 | 10 | 1.5598 | 1.0 | 0.0 | 1.0 | 1.0 |
64
- | 0.8098 | 15.0 | 15 | 1.3913 | 1.0 | 0.0 | 1.0 | 1.0 |
65
- | 0.6939 | 20.0 | 20 | 1.2470 | 1.0 | 0.0 | 1.0 | 1.0 |
66
- | 0.5662 | 25.0 | 25 | 1.0859 | 1.0 | 0.0 | 1.0 | 1.0 |
67
- | 0.4027 | 30.0 | 30 | 0.9390 | 1.0 | 0.0 | 1.0 | 1.0 |
68
- | 0.2595 | 35.0 | 35 | 0.8088 | 1.0 | 0.0 | 1.0 | 1.0 |
69
- | 0.159 | 40.0 | 40 | 0.8187 | 1.0 | 0.0 | 1.0 | 1.0 |
70
- | 0.1225 | 45.0 | 45 | 0.9043 | 1.0 | 0.0 | 1.0 | 1.0 |
71
- | 0.0808 | 50.0 | 50 | 0.9985 | 1.0 | 0.0 | 1.0 | 1.0 |
72
- | 0.0334 | 55.0 | 55 | 1.1227 | 1.0 | 0.0 | 1.0 | 1.0 |
73
- | 0.0121 | 60.0 | 60 | 1.2501 | 1.0 | 0.0 | 1.0 | 1.0 |
74
- | 0.0052 | 65.0 | 65 | 1.3779 | 1.0 | 0.0 | 1.0 | 1.0 |
75
- | 0.0043 | 70.0 | 70 | 1.4248 | 1.0 | 0.0 | 1.0 | 1.0 |
76
 
77
 
78
  ### Framework versions
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/grounded-ai-rag-relevance/runs/oius6vlo)
20
  # grounded-ai-rag-3
21
 
22
  This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 1.3813
25
  - Rouge1: 1.0
26
  - Rouge2: 0.0
27
  - Rougel: 1.0
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 7e-05
48
  - train_batch_size: 2
49
  - eval_batch_size: 8
50
  - seed: 42
51
+ - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 4
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: cosine
55
  - lr_scheduler_warmup_steps: 15
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
61
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
62
+ | 1.7953 | 5.0 | 5 | 1.8076 | 1.0 | 0.0 | 1.0 | 1.0 |
63
+ | 1.4603 | 10.0 | 10 | 1.6034 | 1.0 | 0.0 | 1.0 | 1.0 |
64
+ | 1.2107 | 15.0 | 15 | 1.4092 | 1.0 | 0.0 | 1.0 | 1.0 |
65
+ | 0.911 | 20.0 | 20 | 1.2036 | 1.0 | 0.0 | 1.0 | 1.0 |
66
+ | 0.5225 | 25.0 | 25 | 1.0263 | 1.0 | 0.0 | 1.0 | 1.0 |
67
+ | 0.2248 | 30.0 | 30 | 0.9228 | 1.0 | 0.0 | 1.0 | 1.0 |
68
+ | 0.1138 | 35.0 | 35 | 0.9692 | 1.0 | 0.0 | 1.0 | 1.0 |
69
+ | 0.0533 | 40.0 | 40 | 1.1089 | 1.0 | 0.0 | 1.0 | 1.0 |
70
+ | 0.0197 | 45.0 | 45 | 1.1951 | 1.0 | 0.0 | 1.0 | 1.0 |
71
+ | 0.0066 | 50.0 | 50 | 1.2534 | 1.0 | 0.0 | 1.0 | 1.0 |
72
+ | 0.0051 | 55.0 | 55 | 1.3186 | 1.0 | 0.0 | 1.0 | 1.0 |
73
+ | 0.0036 | 60.0 | 60 | 1.3523 | 1.0 | 0.0 | 1.0 | 1.0 |
74
+ | 0.0047 | 65.0 | 65 | 1.3669 | 1.0 | 0.0 | 1.0 | 1.0 |
75
+ | 0.0037 | 70.0 | 70 | 1.3813 | 1.0 | 0.0 | 1.0 | 1.0 |
76
 
77
 
78
  ### Framework versions
adapter_config.json CHANGED
@@ -11,7 +11,7 @@
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
  "lora_alpha": 32,
14
- "lora_dropout": 0.1,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": null,
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "down_proj",
24
- "v_proj",
25
  "gate_proj",
26
- "q_proj",
27
- "k_proj",
 
28
  "o_proj",
29
- "up_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
  "lora_alpha": 32,
14
+ "lora_dropout": 0.3,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": null,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "gate_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "down_proj",
27
  "o_proj",
28
+ "q_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eee14e572e234fef48bd05e6751732a7be5fcc36a58cb029f509a042420f7e66
3
  size 35668592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3adb363beb9ab4b7603afdf9abfceea13dc71393dd559126e4c5f1df8b239fc
3
  size 35668592
runs/Oct13_18-18-49_48c91bda07e0/events.out.tfevents.1728843530.48c91bda07e0.9895.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933177eae3f100d17cda6870d2222c8910882ec6705c96f62102436ccf46c6e4
3
+ size 22254
runs/Oct13_18-20-53_48c91bda07e0/events.out.tfevents.1728843654.48c91bda07e0.9895.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e741a15fb17b24228f952ec5a01d31346506609fbd23f667f40555841d40097f
3
+ size 4184
runs/Oct13_18-21-27_48c91bda07e0/events.out.tfevents.1728843688.48c91bda07e0.11185.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c9fe55b25f7f812326a5f0f57a62ea987089f6b71af5534caf4645500b3384
3
+ size 16462
runs/Oct13_18-23-33_48c91bda07e0/events.out.tfevents.1728843814.48c91bda07e0.11185.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5d59df0a98e21af953b120fcca1c64f00542da9d6e04adedf5ea7f8d9fa2f3
3
+ size 4184
runs/Oct13_18-24-23_48c91bda07e0/events.out.tfevents.1728843864.48c91bda07e0.12055.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1592c21d085aebf049083aece02af2032530633eec2d56766c9619959270b8c2
3
+ size 17341
runs/Oct13_18-25-58_48c91bda07e0/events.out.tfevents.1728843959.48c91bda07e0.12055.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dafe95867f37ec3f6a9da93b33af24decd93bd74d94d32701e3869060fbc2c2
3
+ size 22047
runs/Oct13_18-26-54_48c91bda07e0/events.out.tfevents.1728844015.48c91bda07e0.12055.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b00a6264d8feea50543db80acbce2b72d2fb9cf3b6969f2b314e15e2daee01
3
+ size 20340
runs/Oct13_18-28-24_48c91bda07e0/events.out.tfevents.1728844105.48c91bda07e0.13277.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db988e43c51d8b4eecf4b01b483d6de0d8341743890ad95aa535fd127d4464d4
3
+ size 29481
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aaa190a3cb68a15b368829d3dff9cf308f2721e76ebc2b27b8b0ec9bc845f20
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a889510aa783638fd8cea9b7ae4b0fa932377333e913d51cf0ca21ff3e6acc08
3
  size 5432