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
d4db261
•
1 Parent(s): a78f671

Model save

Browse files
Files changed (9) hide show
  1. adapter_config.json +4 -4
  2. all_results.json +8 -8
  3. eval_results.json +5 -5
  4. runs/May23_17-23-15_scai5.cs.ucla.edu/events.out.tfevents.1716510216.scai5.cs.ucla.edu.1148301.1 +3 -0
  5. runs/May23_17-24-03_scai5.cs.ucla.edu/events.out.tfevents.1716510252.scai5.cs.ucla.edu.1148436.0 +3 -0
  6. tokenizer.json +1 -6
  7. train_results.json +3 -3
  8. trainer_state.json +6 -6
  9. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "o_proj",
24
- "q_proj",
25
- "down_proj",
26
  "up_proj",
27
- "gate_proj",
28
  "k_proj",
29
- "v_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
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,
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 2.566110134124756,
4
- "eval_runtime": 0.2859,
5
- "eval_samples": 4,
6
- "eval_samples_per_second": 13.992,
7
- "eval_steps_per_second": 3.498,
8
  "train_loss": 1.4264578819274902,
9
- "train_runtime": 2.0986,
10
  "train_samples": 4,
11
- "train_samples_per_second": 1.906,
12
- "train_steps_per_second": 0.477
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
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 2.566110134124756,
4
- "eval_runtime": 0.2859,
5
- "eval_samples": 4,
6
- "eval_samples_per_second": 13.992,
7
- "eval_steps_per_second": 3.498
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
  }
runs/May23_17-23-15_scai5.cs.ucla.edu/events.out.tfevents.1716510216.scai5.cs.ucla.edu.1148301.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7dffe824613da7fca773b37392fb6efbd47d6edfffb21d40832514fc4f8c9a1
3
+ size 354
runs/May23_17-24-03_scai5.cs.ucla.edu/events.out.tfevents.1716510252.scai5.cs.ucla.edu.1148436.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cebaa8888007198a0645dc594003fb9675e1ae7ac03ddba35cf95bf2bc1e2c61
3
+ size 5840
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 2048,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 1.4264578819274902,
4
- "train_runtime": 2.0986,
5
  "train_samples": 4,
6
- "train_samples_per_second": 1.906,
7
- "train_steps_per_second": 0.477
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
  }
trainer_state.json CHANGED
@@ -17,9 +17,9 @@
17
  {
18
  "epoch": 1.0,
19
  "eval_loss": 2.88632869720459,
20
- "eval_runtime": 0.263,
21
- "eval_samples_per_second": 7.604,
22
- "eval_steps_per_second": 3.802,
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": 2.0986,
31
- "train_samples_per_second": 1.906,
32
- "train_steps_per_second": 0.477
33
  }
34
  ],
35
  "logging_steps": 5,
 
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
  "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,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f34f7e356f32afb3f6b92b747a154e8890a05871c5f1c11868b6a2373cc17df
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a78b1b5ecd61c0f19d7e87616d1c69a14e871e3ff14767eec8de5780708ea5ab
3
  size 4920