Hugging Face's logo

AlekseyKorshuk
/
dalio-handwritten-io-1.3b

Text Generation
Transformers
PyTorch
opt
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
AlekseyKorshuk commited on
Commit
2aaf0ca
•
1 Parent(s): 44a1b5d

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +1 -1
  2. train_results.json +1 -1
  3. trainer_state.json +13 -13
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 2.7618001302083335,
4
- "train_runtime": 2178.1486,
5
  "train_samples": 156,
6
  "train_samples_per_second": 0.072,
7
  "train_steps_per_second": 0.001
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 2.7618001302083335,
4
+ "train_runtime": 2178.2199,
5
  "train_samples": 156,
6
  "train_samples_per_second": 0.072,
7
  "train_steps_per_second": 0.001
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 2.7618001302083335,
4
- "train_runtime": 2178.1486,
5
  "train_samples": 156,
6
  "train_samples_per_second": 0.072,
7
  "train_steps_per_second": 0.001
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 2.7618001302083335,
4
+ "train_runtime": 2178.2199,
5
  "train_samples": 156,
6
  "train_samples_per_second": 0.072,
7
  "train_steps_per_second": 0.001
trainer_state.json CHANGED
@@ -9,7 +9,7 @@
9
  "log_history": [
10
  {
11
  "epoch": 0.33,
12
- "learning_rate": 0,
13
  "loss": 2.6917,
14
  "step": 1
15
  },
@@ -17,14 +17,14 @@
17
  "epoch": 0.33,
18
  "eval_accuracy": 0.05304531642224865,
19
  "eval_loss": 2.66796875,
20
- "eval_runtime": 1.8653,
21
- "eval_samples_per_second": 15.547,
22
- "eval_steps_per_second": 0.536,
23
  "step": 1
24
  },
25
  {
26
  "epoch": 0.67,
27
- "learning_rate": 0,
28
  "loss": 2.8435,
29
  "step": 2
30
  },
@@ -32,14 +32,14 @@
32
  "epoch": 0.67,
33
  "eval_accuracy": 0.05304531642224865,
34
  "eval_loss": 2.66796875,
35
- "eval_runtime": 2.1123,
36
- "eval_samples_per_second": 13.729,
37
- "eval_steps_per_second": 0.473,
38
  "step": 2
39
  },
40
  {
41
  "epoch": 1.0,
42
- "learning_rate": 0.0,
43
  "loss": 2.7502,
44
  "step": 3
45
  },
@@ -47,9 +47,9 @@
47
  "epoch": 1.0,
48
  "eval_accuracy": 0.055489496630994846,
49
  "eval_loss": 2.6171875,
50
- "eval_runtime": 1.0076,
51
- "eval_samples_per_second": 28.782,
52
- "eval_steps_per_second": 0.992,
53
  "step": 3
54
  },
55
  {
@@ -57,7 +57,7 @@
57
  "step": 3,
58
  "total_flos": 303365357568.0,
59
  "train_loss": 2.7618001302083335,
60
- "train_runtime": 2178.1486,
61
  "train_samples_per_second": 0.072,
62
  "train_steps_per_second": 0.001
63
  }
 
9
  "log_history": [
10
  {
11
  "epoch": 0.33,
12
+ "learning_rate": 3e-05,
13
  "loss": 2.6917,
14
  "step": 1
15
  },
 
17
  "epoch": 0.33,
18
  "eval_accuracy": 0.05304531642224865,
19
  "eval_loss": 2.66796875,
20
+ "eval_runtime": 1.9177,
21
+ "eval_samples_per_second": 15.122,
22
+ "eval_steps_per_second": 0.521,
23
  "step": 1
24
  },
25
  {
26
  "epoch": 0.67,
27
+ "learning_rate": 3e-05,
28
  "loss": 2.8435,
29
  "step": 2
30
  },
 
32
  "epoch": 0.67,
33
  "eval_accuracy": 0.05304531642224865,
34
  "eval_loss": 2.66796875,
35
+ "eval_runtime": 1.7979,
36
+ "eval_samples_per_second": 16.13,
37
+ "eval_steps_per_second": 0.556,
38
  "step": 2
39
  },
40
  {
41
  "epoch": 1.0,
42
+ "learning_rate": 1.9999999999999998e-05,
43
  "loss": 2.7502,
44
  "step": 3
45
  },
 
47
  "epoch": 1.0,
48
  "eval_accuracy": 0.055489496630994846,
49
  "eval_loss": 2.6171875,
50
+ "eval_runtime": 1.4088,
51
+ "eval_samples_per_second": 20.586,
52
+ "eval_steps_per_second": 0.71,
53
  "step": 3
54
  },
55
  {
 
57
  "step": 3,
58
  "total_flos": 303365357568.0,
59
  "train_loss": 2.7618001302083335,
60
+ "train_runtime": 2178.2199,
61
  "train_samples_per_second": 0.072,
62
  "train_steps_per_second": 0.001
63
  }