Hugging Face's logo

sravanthib
/
s

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
sravanthib commited on
Commit
e3a0e4b
·
verified ·
1 Parent(s): c26d6f2

Training in progress, step 10

Browse files
Files changed (6) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +1 -1
  3. all_results.json +3 -3
  4. train_results.json +3 -3
  5. trainer_state.json +5 -5
  6. training_args.bin +2 -2
adapter_config.json CHANGED
@@ -23,13 +23,13 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
26
  "k_proj",
27
  "o_proj",
 
28
  "gate_proj",
29
- "q_proj",
30
  "up_proj",
31
- "v_proj",
32
- "down_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "v_proj",
27
  "k_proj",
28
  "o_proj",
29
+ "down_proj",
30
  "gate_proj",
 
31
  "up_proj",
32
+ "q_proj"
 
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c17c6d63ee44d5f0f9d7423db898bd7559e2aab1b8b61c7c4cbbfc82051b577
3
  size 40422208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f159dc38b38e0e3c94dd3077585913b1de11b17b0325d48a95db2375a41600
3
  size 40422208
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
- "train_loss": 4.369424438476562,
5
- "train_runtime": 140.6651,
6
- "train_samples_per_second": 1.422,
7
  "train_steps_per_second": 0.071
8
  }
 
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
+ "train_loss": 4.460226058959961,
5
+ "train_runtime": 141.155,
6
+ "train_samples_per_second": 1.417,
7
  "train_steps_per_second": 0.071
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
- "train_loss": 4.369424438476562,
5
- "train_runtime": 140.6651,
6
- "train_samples_per_second": 1.422,
7
  "train_steps_per_second": 0.071
8
  }
 
1
  {
2
  "epoch": 0.2,
3
  "total_flos": 1.7426360578342912e+16,
4
+ "train_loss": 4.460226058959961,
5
+ "train_runtime": 141.155,
6
+ "train_samples_per_second": 1.417,
7
  "train_steps_per_second": 0.071
8
  }
trainer_state.json CHANGED
@@ -11,18 +11,18 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.2,
14
- "grad_norm": 0.32396775484085083,
15
  "learning_rate": 0.0001,
16
- "loss": 4.3694,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.2,
21
  "step": 10,
22
  "total_flos": 1.7426360578342912e+16,
23
- "train_loss": 4.369424438476562,
24
- "train_runtime": 140.6651,
25
- "train_samples_per_second": 1.422,
26
  "train_steps_per_second": 0.071
27
  }
28
  ],
 
11
  "log_history": [
12
  {
13
  "epoch": 0.2,
14
+ "grad_norm": 0.40714770555496216,
15
  "learning_rate": 0.0001,
16
+ "loss": 4.4602,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.2,
21
  "step": 10,
22
  "total_flos": 1.7426360578342912e+16,
23
+ "train_loss": 4.460226058959961,
24
+ "train_runtime": 141.155,
25
+ "train_samples_per_second": 1.417,
26
  "train_steps_per_second": 0.071
27
  }
28
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a15a636d4d7e70698b06a84115b19a8959a8dcf22ad59eec5d7ebb180d2664e
3
- size 9464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b7ae3b730d9211f877480400bed539c92e9d27baaddaee42af78b32b05e19a1
3
+ size 9528