Update README.md
Browse files
README.md
CHANGED
@@ -39,25 +39,25 @@ Use at your own risk. It's a great small model, owing to the base model before t
|
|
39 |
|
40 |
### Training Data
|
41 |
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
|
62 |
### Training Procedure
|
63 |
|
|
|
39 |
|
40 |
### Training Data
|
41 |
|
42 |
+
|
43 |
+
- "eval/loss": 2.1797242164611816,
|
44 |
+
- "_timestamp": 1708624900.2239263,
|
45 |
+
- "_runtime": 20945.370138406754,
|
46 |
+
- "train/train_loss": 2.515587423102269,
|
47 |
+
- "train/global_step": 918,
|
48 |
+
- "train/train_steps_per_second": 0.044,
|
49 |
+
- "train/loss": 2.2062,
|
50 |
+
- "train/learning_rate": 0,
|
51 |
+
- "train/train_samples_per_second": 1.403,
|
52 |
+
- "train/train_runtime": 20945.6359,
|
53 |
+
- "eval/steps_per_second": 4.867,
|
54 |
+
- "eval/samples_per_second": 4.867,
|
55 |
+
- "_step": 923,
|
56 |
+
- "train/epoch": 2.98,
|
57 |
+
- "eval/runtime": 41.0972,
|
58 |
+
- "train/grad_norm": 0.2638521194458008,
|
59 |
+
- "train/total_flos": 141790931224363000
|
60 |
+
|
61 |
|
62 |
### Training Procedure
|
63 |
|