Hugging Face's logo

hllj
/
non-qa-sft-zephyr-7b-beta-v1

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
hllj commited on
Commit
87f16f5
·
1 Parent(s): 23d8999

Model save

Browse files
Files changed (4) hide show
  1. all_results.json +5 -5
  2. eval_results.json +2 -2
  3. train_results.json +3 -3
  4. trainer_state.json +6 -6
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 0.03,
3
  "eval_loss": 0.8876652717590332,
4
- "eval_runtime": 113.7341,
5
  "eval_samples": 650,
6
- "eval_samples_per_second": 5.715,
7
  "eval_steps_per_second": 1.433,
8
  "train_loss": 1.0970729541778566,
9
- "train_runtime": 357.3025,
10
  "train_samples": 5845,
11
- "train_samples_per_second": 0.56,
12
- "train_steps_per_second": 0.14
13
  }
 
1
  {
2
  "epoch": 0.03,
3
  "eval_loss": 0.8876652717590332,
4
+ "eval_runtime": 113.7754,
5
  "eval_samples": 650,
6
+ "eval_samples_per_second": 5.713,
7
  "eval_steps_per_second": 1.433,
8
  "train_loss": 1.0970729541778566,
9
+ "train_runtime": 345.3617,
10
  "train_samples": 5845,
11
+ "train_samples_per_second": 0.579,
12
+ "train_steps_per_second": 0.145
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.03,
3
  "eval_loss": 0.8876652717590332,
4
- "eval_runtime": 113.7341,
5
  "eval_samples": 650,
6
- "eval_samples_per_second": 5.715,
7
  "eval_steps_per_second": 1.433
8
  }
 
1
  {
2
  "epoch": 0.03,
3
  "eval_loss": 0.8876652717590332,
4
+ "eval_runtime": 113.7754,
5
  "eval_samples": 650,
6
+ "eval_samples_per_second": 5.713,
7
  "eval_steps_per_second": 1.433
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.03,
3
  "train_loss": 1.0970729541778566,
4
- "train_runtime": 357.3025,
5
  "train_samples": 5845,
6
- "train_samples_per_second": 0.56,
7
- "train_steps_per_second": 0.14
8
  }
 
1
  {
2
  "epoch": 0.03,
3
  "train_loss": 1.0970729541778566,
4
+ "train_runtime": 345.3617,
5
  "train_samples": 5845,
6
+ "train_samples_per_second": 0.579,
7
+ "train_steps_per_second": 0.145
8
  }
trainer_state.json CHANGED
@@ -29,8 +29,8 @@
29
  {
30
  "epoch": 0.02,
31
  "eval_loss": 0.9467611908912659,
32
- "eval_runtime": 113.3606,
33
- "eval_samples_per_second": 5.734,
34
  "eval_steps_per_second": 1.438,
35
  "step": 25
36
  },
@@ -55,7 +55,7 @@
55
  {
56
  "epoch": 0.03,
57
  "eval_loss": 0.8876652717590332,
58
- "eval_runtime": 114.0086,
59
  "eval_samples_per_second": 5.701,
60
  "eval_steps_per_second": 1.43,
61
  "step": 50
@@ -65,9 +65,9 @@
65
  "step": 50,
66
  "total_flos": 4008716634423296.0,
67
  "train_loss": 1.0970729541778566,
68
- "train_runtime": 357.3025,
69
- "train_samples_per_second": 0.56,
70
- "train_steps_per_second": 0.14
71
  }
72
  ],
73
  "logging_steps": 10,
 
29
  {
30
  "epoch": 0.02,
31
  "eval_loss": 0.9467611908912659,
32
+ "eval_runtime": 113.3365,
33
+ "eval_samples_per_second": 5.735,
34
  "eval_steps_per_second": 1.438,
35
  "step": 25
36
  },
 
55
  {
56
  "epoch": 0.03,
57
  "eval_loss": 0.8876652717590332,
58
+ "eval_runtime": 114.0209,
59
  "eval_samples_per_second": 5.701,
60
  "eval_steps_per_second": 1.43,
61
  "step": 50
 
65
  "step": 50,
66
  "total_flos": 4008716634423296.0,
67
  "train_loss": 1.0970729541778566,
68
+ "train_runtime": 345.3617,
69
+ "train_samples_per_second": 0.579,
70
+ "train_steps_per_second": 0.145
71
  }
72
  ],
73
  "logging_steps": 10,