Hugging Face's logo

VedaantJain
/
llama_check_tuned

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
alignment-handbook
trl
sft
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
VedaantJain commited on
Commit
b7bf962
·
verified ·
1 Parent(s): 3d4ad8c

Model save

Browse files
Files changed (6) hide show
  1. all_results.json +8 -3
  2. eval_results.json +8 -0
  3. tokenizer.json +2 -2
  4. train_results.json +3 -3
  5. trainer_state.json +9 -9
  6. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,9 +1,14 @@
1
  {
2
  "epoch": 2.0,
 
 
 
 
 
3
  "total_flos": 239345474732032.0,
4
  "train_loss": 1.1433531045913696,
5
- "train_runtime": 2.3713,
6
  "train_samples": 10,
7
- "train_samples_per_second": 8.434,
8
- "train_steps_per_second": 0.843
9
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "eval_loss": 1.131566047668457,
4
+ "eval_runtime": 0.185,
5
+ "eval_samples": 10,
6
+ "eval_samples_per_second": 54.065,
7
+ "eval_steps_per_second": 10.813,
8
  "total_flos": 239345474732032.0,
9
  "train_loss": 1.1433531045913696,
10
+ "train_runtime": 2.1475,
11
  "train_samples": 10,
12
+ "train_samples_per_second": 9.313,
13
+ "train_steps_per_second": 0.931
14
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 1.131566047668457,
4
+ "eval_runtime": 0.185,
5
+ "eval_samples": 10,
6
+ "eval_samples_per_second": 54.065,
7
+ "eval_steps_per_second": 10.813
8
+ }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fca926fdfedcb8fd225765fb3911e0ab5de0390ec7242a46dff829e8604f723
3
- size 17210020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
train_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 2.0,
3
  "total_flos": 239345474732032.0,
4
  "train_loss": 1.1433531045913696,
5
- "train_runtime": 2.3713,
6
  "train_samples": 10,
7
- "train_samples_per_second": 8.434,
8
- "train_steps_per_second": 0.843
9
  }
 
2
  "epoch": 2.0,
3
  "total_flos": 239345474732032.0,
4
  "train_loss": 1.1433531045913696,
5
+ "train_runtime": 2.1475,
6
  "train_samples": 10,
7
+ "train_samples_per_second": 9.313,
8
+ "train_steps_per_second": 0.931
9
  }
trainer_state.json CHANGED
@@ -17,17 +17,17 @@
17
  {
18
  "epoch": 1.0,
19
  "eval_loss": 1.131566047668457,
20
- "eval_runtime": 0.156,
21
- "eval_samples_per_second": 64.102,
22
- "eval_steps_per_second": 12.82,
23
  "step": 1
24
  },
25
  {
26
  "epoch": 2.0,
27
  "eval_loss": 1.131566047668457,
28
- "eval_runtime": 0.1552,
29
- "eval_samples_per_second": 64.444,
30
- "eval_steps_per_second": 12.889,
31
  "step": 2
32
  },
33
  {
@@ -35,9 +35,9 @@
35
  "step": 2,
36
  "total_flos": 239345474732032.0,
37
  "train_loss": 1.1433531045913696,
38
- "train_runtime": 2.3713,
39
- "train_samples_per_second": 8.434,
40
- "train_steps_per_second": 0.843
41
  }
42
  ],
43
  "logging_steps": 5,
 
17
  {
18
  "epoch": 1.0,
19
  "eval_loss": 1.131566047668457,
20
+ "eval_runtime": 0.1561,
21
+ "eval_samples_per_second": 64.049,
22
+ "eval_steps_per_second": 12.81,
23
  "step": 1
24
  },
25
  {
26
  "epoch": 2.0,
27
  "eval_loss": 1.131566047668457,
28
+ "eval_runtime": 0.156,
29
+ "eval_samples_per_second": 64.111,
30
+ "eval_steps_per_second": 12.822,
31
  "step": 2
32
  },
33
  {
 
35
  "step": 2,
36
  "total_flos": 239345474732032.0,
37
  "train_loss": 1.1433531045913696,
38
+ "train_runtime": 2.1475,
39
+ "train_samples_per_second": 9.313,
40
+ "train_steps_per_second": 0.931
41
  }
42
  ],
43
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ebe46d98a6851b85db4ef6908bb9fe0d07ebbd0ec3ef607f14f955f2a49ead0
3
  size 6968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd541300d16094dde613b3efb4ae74aef23af07c3a455f9ca7290f37b369a25a
3
  size 6968