Hugging Face's logo

AKTaylor98
/
Llama2-7b-sft-qlora

PEFT
TensorBoard
Safetensors
llama
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
AKTaylor98 commited on
Commit
593b042
•
1 Parent(s): d4db261

Model save

Browse files
Files changed (8) hide show
  1. adapter_config.json +4 -4
  2. all_results.json +6 -6
  3. eval_results.json +3 -3
  4. runs/May23_17-24-03_scai5.cs.ucla.edu/events.out.tfevents.1716510263.scai5.cs.ucla.edu.1148436.1 +3 -0
  5. runs/May23_18-42-13_scai5.cs.ucla.edu/events.out.tfevents.1716514941.scai5.cs.ucla.edu.1152718.0 +3 -0
  6. train_results.json +3 -3
  7. trainer_state.json +6 -6
  8. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "gate_proj",
 
24
  "o_proj",
25
- "up_proj",
26
  "v_proj",
27
- "k_proj",
28
- "down_proj",
29
- "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "down_proj",
24
  "gate_proj",
25
+ "q_proj",
26
  "o_proj",
 
27
  "v_proj",
28
+ "up_proj",
29
+ "k_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 1.0,
3
  "eval_loss": 2.88632869720459,
4
- "eval_runtime": 0.2446,
5
  "eval_samples": 2,
6
- "eval_samples_per_second": 8.177,
7
- "eval_steps_per_second": 4.088,
8
  "train_loss": 1.4264578819274902,
9
- "train_runtime": 2.1851,
10
  "train_samples": 4,
11
- "train_samples_per_second": 1.831,
12
- "train_steps_per_second": 0.458
13
  }
 
1
  {
2
  "epoch": 1.0,
3
  "eval_loss": 2.88632869720459,
4
+ "eval_runtime": 0.2079,
5
  "eval_samples": 2,
6
+ "eval_samples_per_second": 9.62,
7
+ "eval_steps_per_second": 4.81,
8
  "train_loss": 1.4264578819274902,
9
+ "train_runtime": 2.0125,
10
  "train_samples": 4,
11
+ "train_samples_per_second": 1.988,
12
+ "train_steps_per_second": 0.497
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "eval_loss": 2.88632869720459,
4
- "eval_runtime": 0.2446,
5
  "eval_samples": 2,
6
- "eval_samples_per_second": 8.177,
7
- "eval_steps_per_second": 4.088
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "eval_loss": 2.88632869720459,
4
+ "eval_runtime": 0.2079,
5
  "eval_samples": 2,
6
+ "eval_samples_per_second": 9.62,
7
+ "eval_steps_per_second": 4.81
8
  }
runs/May23_17-24-03_scai5.cs.ucla.edu/events.out.tfevents.1716510263.scai5.cs.ucla.edu.1148436.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2a9a352756fff7f4010579cf0d8a68887ab4364b48c62f8d1fd52bc9a2d39c8
3
+ size 354
runs/May23_18-42-13_scai5.cs.ucla.edu/events.out.tfevents.1716514941.scai5.cs.ucla.edu.1152718.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b392b2c9ee70fb52a44a271ea1599e6c696e1a63f00a309beb23d56a3c9a77
3
+ size 5840
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 1.4264578819274902,
4
- "train_runtime": 2.1851,
5
  "train_samples": 4,
6
- "train_samples_per_second": 1.831,
7
- "train_steps_per_second": 0.458
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 1.4264578819274902,
4
+ "train_runtime": 2.0125,
5
  "train_samples": 4,
6
+ "train_samples_per_second": 1.988,
7
+ "train_steps_per_second": 0.497
8
  }
trainer_state.json CHANGED
@@ -17,9 +17,9 @@
17
  {
18
  "epoch": 1.0,
19
  "eval_loss": 2.88632869720459,
20
- "eval_runtime": 0.2519,
21
- "eval_samples_per_second": 7.939,
22
- "eval_steps_per_second": 3.97,
23
  "step": 1
24
  },
25
  {
@@ -27,9 +27,9 @@
27
  "step": 1,
28
  "total_flos": 32602467598336.0,
29
  "train_loss": 1.4264578819274902,
30
- "train_runtime": 2.1851,
31
- "train_samples_per_second": 1.831,
32
- "train_steps_per_second": 0.458
33
  }
34
  ],
35
  "logging_steps": 5,
 
17
  {
18
  "epoch": 1.0,
19
  "eval_loss": 2.88632869720459,
20
+ "eval_runtime": 0.2186,
21
+ "eval_samples_per_second": 9.149,
22
+ "eval_steps_per_second": 4.574,
23
  "step": 1
24
  },
25
  {
 
27
  "step": 1,
28
  "total_flos": 32602467598336.0,
29
  "train_loss": 1.4264578819274902,
30
+ "train_runtime": 2.0125,
31
+ "train_samples_per_second": 1.988,
32
+ "train_steps_per_second": 0.497
33
  }
34
  ],
35
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a78b1b5ecd61c0f19d7e87616d1c69a14e871e3ff14767eec8de5780708ea5ab
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3293de4eefc9334f4578398340ab73579e065f965c7ea5d261099e9014875abc
3
  size 4920